| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01881467544684854, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006271558482282847, | |
| "eval_loss": 2.3863885402679443, | |
| "eval_runtime": 80.4527, | |
| "eval_samples_per_second": 8.353, | |
| "eval_steps_per_second": 4.176, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018814675446848542, | |
| "grad_norm": 1.2381781339645386, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3866, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0037629350893697085, | |
| "grad_norm": 0.9829408526420593, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3178, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005017246785826278, | |
| "eval_loss": 1.9485021829605103, | |
| "eval_runtime": 81.0377, | |
| "eval_samples_per_second": 8.292, | |
| "eval_steps_per_second": 4.146, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005644402634054563, | |
| "grad_norm": 0.6054725050926208, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0117, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007525870178739417, | |
| "grad_norm": 0.7741472125053406, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.9244, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00940733772342427, | |
| "grad_norm": 0.9158235788345337, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.8141, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010034493571652555, | |
| "eval_loss": 1.699448585510254, | |
| "eval_runtime": 81.4406, | |
| "eval_samples_per_second": 8.251, | |
| "eval_steps_per_second": 4.126, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011288805268109126, | |
| "grad_norm": 0.6685766577720642, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.726, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01317027281279398, | |
| "grad_norm": 0.8459041118621826, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.595, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015051740357478834, | |
| "grad_norm": 0.6135718822479248, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.6415, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.015051740357478834, | |
| "eval_loss": 1.643975019454956, | |
| "eval_runtime": 80.9114, | |
| "eval_samples_per_second": 8.305, | |
| "eval_steps_per_second": 4.153, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016933207902163686, | |
| "grad_norm": 0.5688802599906921, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.8074, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01881467544684854, | |
| "grad_norm": 0.5277060270309448, | |
| "learning_rate": 0.0, | |
| "loss": 1.6516, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9916411753267200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |